{ "openapi": "3.0.1", "info": { "title": "Documents to Markdown/JSON for RAG (PDF, Office, OCR)", "version": "0.1", "x-build-id": "9em6LrOklnJOrIYKl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bravona~docs-to-markdown-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bravona-docs-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bravona~docs-to-markdown-rag/runs": { "post": { "operationId": "runs-sync-bravona-docs-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bravona~docs-to-markdown-rag/run-sync": { "post": { "operationId": "run-sync-bravona-docs-to-markdown-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Public, logged-out links to PDF, DOCX, PPTX, XLSX, CSV, HTML, plain-text or image files. The format is detected from the file itself. robots.txt is respected and each host is fetched at most once per second; pages behind a login, paywall or captcha are reported as errors, never bypassed.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyValueStoreId": { "title": "Key-value store with files (optional)", "type": "string", "description": "Convert files you uploaded to one of your Apify key-value stores. Every record in the store is converted unless you list keys below." }, "keyValueStoreKeys": { "title": "Keys to convert", "type": "array", "description": "Record keys in the store above. Leave empty to convert every record (except INPUT).", "items": { "type": "string" } }, "ocrMode": { "title": "OCR", "enum": [ "auto", "off", "force" ], "type": "string", "description": "auto: OCR only pages that have no text layer (scans, photos). off: never OCR (such pages come back empty and are not charged). force: OCR every page, even ones with text.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "type": "string", "description": "Tesseract language code(s): eng, deu, fra, spa, ita, por, nld. Combine with +, e.g. eng+deu.", "default": "eng" }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are not downloaded; they get an error record and are not charged. Maximum 100.", "default": 25 }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 1000, "type": "integer", "description": "PDF pages, slides, or 3,000-character blocks for formats without pages. Maximum 1,000.", "default": 200 }, "onPageLimit": { "title": "When a document is over the page cap", "enum": [ "truncate", "fail" ], "type": "string", "description": "truncate: convert and charge only the first pages up to the cap. fail: skip the document with an error record (not charged).", "default": "truncate" }, "maxOcrPagesPerDocument": { "title": "Max OCR pages per document", "minimum": 0, "maximum": 500, "type": "integer", "description": "Pages past this that need OCR are returned empty, flagged ocrSkipped, and not charged. 0 disables OCR. Maximum 500.", "default": 50 }, "maxDocuments": { "title": "Max documents per run", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Documents after this are not processed. Maximum 2,000.", "default": 100 }, "maxConcurrency": { "title": "Documents in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents are converted at once. More needs more memory (OCR uses about 300 MB per document in flight).", "default": 2 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "How long to wait for one file to download before giving up on it (error record TIMEOUT, not charged).", "default": 60 }, "includeMarkdown": { "title": "Include full Markdown", "type": "boolean", "description": "The whole document as one Markdown string.", "default": true }, "includePages": { "title": "Include per-page Markdown", "type": "boolean", "description": "One entry per page with its page number, text and OCR flags.", "default": true }, "includeChunks": { "title": "Include RAG chunks", "type": "boolean", "description": "Heading-aware chunks with pageStart/pageEnd and the heading path, ready to embed.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Target maximum characters per chunk. Chunks break at headings, paragraphs and table rows; split tables repeat their header row.", "default": 1500 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Text repeated from the end of the previous chunk; at most half the chunk size.", "default": 150 }, "includeSpeakerNotes": { "title": "Include PPTX speaker notes", "type": "boolean", "description": "For PowerPoint files, add each slide's speaker notes under the slide text.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }